5
$\begingroup$

Suppose I have $\lbrace x_i,y_i\rbrace_{i=1}^n$ and I have $$y_i = \beta_0 + \beta_1 x_i + \epsilon_i$$ and we have the usual assumptions for OLS. The equation for $\hat{\beta}_1$ is

\begin{align*} \hat{\beta}_1 &= \frac{\sum_{i=1}^n (x_i-\bar{x})(y_i-\bar{y})}{\sum_{i=1}^n(x_i -\bar{x})^2} \\&= \sum_{i=1}^n\frac{ (x_i-\bar{x})}{\sum_{i=1}^n(x_i -\bar{x})^2}y_i - \bar{y}\frac{\sum_{i=1}^n (x_i-\bar{x})}{\sum_{i=1}^n(x_i -\bar{x})^2}\\ \end{align*}

My teacher wrote that we can say

$$\hat{\beta}_1 = \sum_{i=1}^n c_i y_i$$

where $c_i = \frac{ (x_i-\bar{x})}{\sum_{i=1}^n(x_i -\bar{x})^2}$

I don't see how this makes sense. There is clearly a term on the far right that involves the $\bar{y}$. Are there certain situations where we can ignore the $\bar{y}$ term?

$\endgroup$
6
$\begingroup$

The second term is zero because:

$$\sum_i (x_i - \bar x) = \sum_i x_i - n \bar x = n \bar x - n \bar x = 0$$

This is a trick that comes up pretty often, so it's nice to have an eye for spotting it.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.